/**
* Used to compare between clusters. If this cluster is better, meaning less
* deviation, returns a negative number so that it is put first when sorted.
*/
public int CompareTo(Cluster other, DocumentAnalyzer analyzer)
{
// TODO: Find better method, this one favors smaller clusters
// Put clusters with only one article at the ends
if (Documents.Count == 1)
{
return(1);
}
if (other.Documents.Count == 1)
{
return(-1);
}
double simA, simB;
simA = simB = 0;
foreach (int i in this.Documents)
{
simA += analyzer.Similarity(this.Centroid, i);
}
foreach (int i in other.Documents)
{
simB += analyzer.Similarity(other.Centroid, i);
}
simA /= this.Documents.Count;
simB /= other.Documents.Count;
if (simA > simB)
{
return(-1);
}
else if (simA < simB)
{
return(1);
}
else
{
return(0);
}
}
/**
* Returns an array of clusters of size k with clusters sorted by least
* deviation between articles and articles within each cluster sorted
* by greatest similarity to that cluster's centroid
*/
public Cluster[] cluster(int k)
{
// Possible improvement: limit min/max cluster size
var clusters = new Cluster[k];
var r = new Random();
// Initialize k clusters by choosing random documents as starting points
for (int i = 0; i < k; i++)
{
clusters[i] = new Cluster();
bool run = true;
int count1 = 0;
while (run && count1 < 10)
{
count1++;
// Choose random document to initialize cluster to
int index = (int)(r.NextDouble() * articles.Count);
clusters[i].Centroid = analyzer.GetDocumentTfIdf(index);
bool continueRunning = false;
for (int j = 0; j < i; j++)
{
// Keep running if this cluster is too similar to an already chosen cluster
if (analyzer.Similarity(clusters[j].Centroid, clusters[i].Centroid) >= 0.1)
{
continueRunning = true;
break;
}
}
run = continueRunning;
}
}
int count2 = 0;
bool stillChanging = true;
while (stillChanging && count2 < 20)
{
count2++;
foreach (Cluster c in clusters)
{
c.Documents.Clear();
}
// Assign each article the cluster it's closest to
for (int i = 0; i < articles.Count; i++)
{
double greatestSim = 0;
int clusterIndex = 0;
for (int j = 0; j < clusters.Length; j++)
{
double currentSim = analyzer.Similarity(clusters[j].Centroid, i);
if (currentSim > greatestSim)
{
greatestSim = currentSim;
clusterIndex = j;
}
}
clusters[clusterIndex].Documents.Add(i);
}
// Update cluster centroids
var newCentroids = new double[clusters.Length][];
for (int i = 0; i < clusters.Length; i++)
{
var newCentroid = new double[analyzer.NumberOfTerms()];
var currDocs = clusters[i].Documents;
for (int j = 0; j < currDocs.Count; j++)
{
var values = analyzer.GetDocumentTfIdf(currDocs[j]);
for (int l = 0; l < newCentroid.Length; l++)
{
newCentroid[l] += values[l];
}
}
for (int j = 0; j < newCentroid.Length; j++)
{
newCentroid[j] /= currDocs.Count;
}
newCentroids[i] = newCentroid;
}
// Finish if clusters remain unchanged
bool unchanged = true;
for (int i = 0; i < clusters.Length; i++)
{
if (!newCentroids[i].SequenceEqual(clusters[i].Centroid))
{
unchanged = false;
clusters[i].Centroid = newCentroids[i];
}
}
stillChanging = !unchanged;
}
// Sort by best clusters and best articles within each cluster
Array.Sort(clusters, (Cluster x, Cluster y) => x.CompareTo(y, analyzer));
foreach (Cluster c in clusters)
{
c.Documents.Sort((int x, int y) => analyzer.Compare(x, y, c.Centroid));
}
// Map from indexes to the actual NewsArticles and add to clusters
foreach (Cluster c in clusters)
{
foreach (int index in c.Documents)
{
c.Articles.Add(articles[index]);
}
}
return(clusters);
}
